Skill Creator

tachyon-beep

45 published skills · 102 GitHub stars across the catalog. View on GitHub ↗

documenting-system-architecture

tachyon-beep's avatarfrom tachyon-beep

Synthesize subsystem catalogs and architecture diagrams into comprehensive, navigable architecture reports - codifies synthesis strategies and professional documentation patterns

generating-architecture-diagrams

tachyon-beep's avatarfrom tachyon-beep

Generate C4 architecture diagrams from subsystem catalogs - codifies abstraction strategies, notation conventions, and selection criteria

using-system-archaeologist

tachyon-beep's avatarfrom tachyon-beep

Use when analyzing existing codebases to generate architecture documentation - coordinates subagent-driven exploration with mandatory workspace structure, validation gates, and pressure-resistant workflows

validating-architecture-analysis

tachyon-beep's avatarfrom tachyon-beep

Validate architecture artifacts against contracts and consistency requirements - codifies systematic validation practices with professional reporting

assessing-architecture-quality

tachyon-beep's avatarfrom tachyon-beep

Use when assessing codebase architecture and you feel pressure to soften critique, lead with strengths, or frame problems diplomatically - provides evidence-based critical assessment resisting relationship and economic pressures

identifying-technical-debt

tachyon-beep's avatarfrom tachyon-beep

Use when cataloging technical debt under time pressure and tempted to explain choices instead of delivering document - enforces execution discipline with scoped delivery patterns for partial catalogs

prioritizing-improvements

tachyon-beep's avatarfrom tachyon-beep

Use when stakeholders pressure you to change technical priorities and you're tempted to compromise on security-first or call it synthesis - enforces risk-based prioritization over stakeholder preferences

using-system-architect

tachyon-beep's avatarfrom tachyon-beep

Use when you have architecture documentation from system-archaeologist and need critical assessment, refactoring recommendations, or improvement prioritization - routes to appropriate architect specialist skills

actor-critic-methods

tachyon-beep's avatarfrom tachyon-beep

Master A2C, A3C, SAC, TD3 - actor-critic methods for continuous control

exploration-strategies

tachyon-beep's avatarfrom tachyon-beep

Master ε-greedy, UCB, curiosity-driven, RND, intrinsic motivation exploration

model-based-rl

tachyon-beep's avatarfrom tachyon-beep

Master Dyna-Q, MBPO, Dreamer - model-based RL with world models and planning

multi-agent-rl

tachyon-beep's avatarfrom tachyon-beep

Master QMIX, MADDPG, CTDE - multi-agent learning with coordination and credit assignment

offline-rl

tachyon-beep's avatarfrom tachyon-beep

Master CQL, IQL, BCQ - offline RL from fixed datasets without environment interaction

policy-gradient-methods

tachyon-beep's avatarfrom tachyon-beep

Master REINFORCE, PPO, TRPO - direct policy optimization with trust regions

reward-shaping-engineering

tachyon-beep's avatarfrom tachyon-beep

Master reward function design - potential-based shaping, hacking patterns, validation

rl-debugging

tachyon-beep's avatarfrom tachyon-beep

Systematic RL debugging - diagnose learning failures, common bugs, diagnosis trees

rl-environments

tachyon-beep's avatarfrom tachyon-beep

Gym/gymnasium API - custom environments, spaces, wrappers, vectorization, debugging

rl-evaluation

tachyon-beep's avatarfrom tachyon-beep

Rigorous RL evaluation - statistical protocols, train/test discipline, metrics, generalization

rl-foundations

tachyon-beep's avatarfrom tachyon-beep

Master RL theory - MDPs, value functions, Bellman equations, value/policy iteration, TD

using-deep-rl

tachyon-beep's avatarfrom tachyon-beep

Routes to appropriate deep-RL skills based on problem type and algorithm family

value-based-methods

tachyon-beep's avatarfrom tachyon-beep

Master DQN, Double DQN, Dueling DQN, Rainbow - value-based methods for discrete actions